Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add seansmithworks/impeccable-swift --skill impeccablegit clone --depth 1 https://github.com/seansmithworks/impeccable-swiftWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/seansmithworks/impeccable-swift/impeccable)<a href="https://agentmods.dev/skills/seansmithworks/impeccable-swift/impeccable"><img src="https://agentmods.dev/badge/skills/seansmithworks/impeccable-swift/impeccable/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/seansmithworks/impeccable-swift/impeccable"><img src="https://agentmods.dev/badge/skills/seansmithworks/impeccable-swift/impeccable.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00367 | $0.04277 |
| Opus 5.5 | $0.00147 | $0.01711 |
| Sonnet 5.5 | $0.00073 | $0.00855 |
| Haiku 4.5 | $0.00037 | $0.00428 |
Grade A, and why
impeccable-swift scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Designs and iterates production-grade SwiftUI interfaces for Apple platforms. Real working code, committed design choices, exceptional craft. Points not pixels, Liquid Glass materials, SF Symbols, Dynamic Type, and Apple HIG defaults — not the beige, rounded-rect "AI SwiftUI" every model reaches for by default.
Setup (non-optional)
Two steps before any design work. Both are required. Skipping either produces generic output that ignores the project.
1. Context gathering
Two files at the project root, case-insensitive:
- PRODUCT.md — required. Users, brand, tone, anti-references, strategic principles.
- DESIGN.md — optional, strongly recommended. Color Sets, typography (SF Pro / custom), spacing, components.
Load both in one call:
node .claude/skills/impeccable-swift/scripts/load-context.mjs
Consume the full JSON output. Never pipe through head, tail, grep, or jq.
If the output is already in this session's conversation history, don't re-run. Exceptions requiring a fresh load: you just ran /impeccable-swift teach or /impeccable-swift document (they rewrite the files), or the user manually edited one.
If PRODUCT.md is missing, empty, or placeholder ([TODO] markers, <200 chars): run /impeccable-swift teach, then resume the user's original task with the fresh context.
If DESIGN.md is missing: nudge once per session ("Run /impeccable-swift document for more on-brand output"), then proceed.
2. Register
Every design task is brand (marketing SwiftUI shells, landing surfaces, campaign pages, portfolio apps — design IS the product) or product (app UI, dashboards, admin tools, utilities — design SERVES the product).
Identify before designing. Priority: (1) cue in the task itself ("marketing shell" vs "settings screen"); (2) the surface in focus (the view, file, or feature being worked on); (3) register field in PRODUCT.md. First match wins.
If PRODUCT.md lacks the register field (legacy), infer it once from its "Users" and "Product Purpose" sections, then cache the inferred value for the session. Suggest the user run /impeccable-swift teach to add the field explicitly.
What ships with it
45 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/.gitkeep 0 B
- reference/accessibility.md 13 KB
- reference/adapt.md 13 KB
- reference/animate.md 15 KB
- reference/audit.md 16 KB
- reference/bolder.md 11 KB
- reference/brand.md 19 KB
- reference/clarify.md 8.8 KB
- reference/codex.md 13 KB
- reference/cognitive-load.md 13 KB
- reference/color-and-contrast.md 9.7 KB
- reference/colorize.md 13 KB
- reference/craft.md 11 KB
- reference/critique.md 17 KB
- reference/delight.md 20 KB
- reference/distill.md 7.5 KB
- reference/document.md 35 KB
- reference/extract.md 8.0 KB
- reference/harden.md 24 KB
- reference/heuristics-scoring.md 18 KB
- reference/interaction-design.md 13 KB
- reference/ios-vs-macos.md 7.0 KB
- reference/layout.md 15 KB
- reference/live.md 5.3 KB
- reference/materials.md 8.6 KB
- reference/motion-design.md 6.7 KB
- reference/navigation.md 10 KB
- reference/onboard.md 12 KB
- reference/optimize.md 15 KB
- reference/overdrive.md 15 KB
- reference/personas.md 15 KB
- reference/polish.md 18 KB
- reference/product.md 11 KB
- reference/quieter.md 8.1 KB
- reference/responsive-design.md 11 KB
- reference/sf-symbols.md 5.5 KB
- reference/shape.md 18 KB
- reference/spatial-design.md 7.6 KB
- reference/teach.md 13 KB
- reference/typeset.md 12 KB
- reference/typography.md 17 KB
- reference/ux-writing.md 9.0 KB
- scripts/command-metadata.json 9.9 KB
- scripts/load-context.mjs 2.9 KB runs code
- scripts/pin.mjs 6.6 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 211 lines · 367 tokens per session scan A 37680e813ec3
impeccable-swift is a skill published in the GitHub repository seansmithworks/impeccable-swift (7 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 367 tokens to every session and 4,277 once invoked, about $0.0015 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
impeccable-swift compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| impeccable-swiftseansmithworks/impeccable-swift | Skill | 7 | 5mo ago | Apache-2.0 | A | 367 | Claude Code |
| gamified-appnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| mobile-appnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 79 | Claude Code, Codex |
| wireframe-mobile-flownexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 141 | Claude Code, Codex |
| mobile-onboardingnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 65 | Claude Code, Codex |
| figma-a11y-annotationscvs-health/ios-swiftui-accessibility-techniques | Skill | 388 | yesterday | Apache-2.0 | A | 110 | Claude Code, Codex |
| iOS SwiftUI Accessibilitycvs-health/ios-swiftui-accessibility-techniques | Skill | 388 | yesterday | Apache-2.0 | A | 67 | Claude Code, Codex |